No abstract
Introduction: Modern advances in acute stroke care place an added emphasis on accurate prehospital diagnosis and triage. As part of the Improving Treatment with Rapid Evaluation of Acute Stroke via mobile Telemedicine (iTREAT) study, we assessed the EMS provider experience with a novel system for mobile telestroke assessment. Methods: We developed a 12-question survey with input from local participants in an EMS Council serving rural counties in central Virginia. Providers rated the iTREAT system on feasibility for acute stroke triage, potential effectiveness in prehospital neurological assessment, and interactions with prehospital care. All survey responses were voluntary and anonymous. Results: Since initiation of live patient enrollment, we have completed 34 ambulance-based telestroke encounters with the iTREAT system. Among 7 participating agencies, 19 EMS providers have served as tele-presenters during the telestroke assessment, and 17 EMS providers completed the voluntary survey. Of the respondents, 71% were certified EMS providers for over 5 years. Regarding technical feasibility, 69% experienced issues related to maintaining a video connection, 41% with logging in to the videoconferencing application, and 18% powering on the tablet. Of technical challenges, 41% of providers resolved the issue on their own, 18% with guidance from study staff, and 24% could not resolve the issue. Concerning patient care, 23% felt the system interfered, 35% were neutral, and 41% felt there was no interference. The majority of respondents (71%) agreed that the iTREAT system is feasible for acute stroke triage, and an effective tool (59%) for prehospital neurological assessment. In commentary, EMS participants emphasized the system’s utility in rural areas. Conclusion: This survey of the EMS experience with a low-cost, ambulance-based system for prehospital telestroke assessment reveals both technical challenges and clinical promise. Importantly, technical issues are mostly solvable in real time and correctable for further system refinement. As a novel tool for prehospital neurological assessment and acute stroke triage, the initial EMS evaluation supports further investigation of clinical efficacy, particularly in rural and underserved areas.
BackgroundCurrent EMS stroke screening tools facilitate early detection and triage, but the tools' accuracy and reliability are limited and highly variable. An automated stroke screening tool could improve stroke outcomes by facilitating more accurate prehospital diagnosis and delivery. We hypothesize that a machine learning algorithm using video analysis can detect common signs of stroke. As a proof-of-concept study, we trained a computer algorithm to detect presence and laterality of facial weakness in publically available videos with comparable accuracy, sensitivity, and specificity to paramedics.Methods and ResultsWe curated videos of people with unilateral facial weakness (n = 93) and with a normal smile (n = 96) from publicly available web-based sources. Three board certified vascular neurologists categorized the videos according to the presence or absence of weakness and laterality. Three paramedics independently analyzed each video with a mean accuracy, sensitivity and specificity of 92.6% [95% CI 90.1–94.7%], 87.8% [95% CI 83.9–91.7%] and 99.3% [95% CI 98.2–100%]. Using a 5-fold cross validation scheme, we trained a computer vision algorithm to analyze the same videos producing an accuracy, sensitivity and specificity of 88.9% [95% CI 83.5–93%], 90.3% [95% CI 82.4–95.5%] and 87.5 [95% CI 79.2–93.4%].ConclusionsThese preliminary results suggest that a machine learning algorithm using computer vision analysis can detect unilateral facial weakness in pre-recorded videos with an accuracy and sensitivity comparable to trained paramedics. Further research is warranted to pursue the concept of augmented facial weakness detection and external validation of this algorithm in independent data sets and prospective patient encounters.
Introduction: Acute strokes necessitate streamlined communication between first responders and physicians regarding stroke signs ascertained in the field. Stroke alert protocols that dictate hospital resource activation contribute to the speed in which potential cases are assessed and treated. We studied associations between EMS stroke pre-notification and ED stroke alert activation behavior at a Comprehensive Stroke Center. Methods: This retrospective chart review identified patients who arrived via EMS and were ultimately stroke alerted from the ED between April 2020 and July 2021. Data was collected manually through a state-wide EMS record exchange and internal hospital databases to include EMS documentation of attempts to alert the ED to stroke, time of ED stroke alert activation, and final discharge diagnosis. Descriptive statistics are presented as counts and percentages. Results: Among the 472 cases of stroke alerted patients, 214 (45.3%) were discharged with a final diagnosis of acute stroke. There were 167 (35.4%) patients where EMS documented attempts to pre-notify the hospital of a potential stroke, versus 210 (45%) whose records lacked explicit note of pre-notification. EMS records could not be found in 94 (20.2%) cases. Among 167 known cases where EMS attempted hospital pre-notification, the ED activated a stroke alert prior to hospital arrival in 69 (41.3%). Among 210 cases where EMS did not record pre-notification, the ED stroke pre-alerted 23 (11.0%), suggesting gaps in EMS documentation of completed stroke pre-notifications. Of 94 patients who lacked EMS records, 29 (30.9%) were pre-alerted to stroke by the ED. Finally, among 214 patients discharged with acute stroke, 96 (44.9%) had documented EMS stroke pre-notifications, of which 46 (21.5%) received ED pre-alerts. An additional 24 (11.2%) stroke patients who lacked sufficient documentation were stroke alerted by the ED prior to hospital arrival. Conclusions: Quality in communications spanning from EMS to physicians is a crucial prerequisite to timely stroke care. Gaps in EMS records and ED stroke alert activation lend support to a need for standardization in stroke documentation and stroke alert protocols, which may streamline data access and improve patient experience of care.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
customersupport@researchsolutions.com
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
This site is protected by reCAPTCHA and the Google Privacy Policy and Terms of Service apply.
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.